IMPLEMENTATION OF CLAHE CONTRAST ENHANCEMENT & OTSU THRESHOLDING IN RETINAL IMAGE PROCESSING

In both ophthalmological and cardiovascular disease diagnosis, the accurate segmentation of retinal vessel tree has become prerequisite step for automatic or computer-aided diagnosis systems. Unlike typical foreground background in normal image processing, there are three problems making task even harder. First, color tends to be red everywhere, thus having a lower contrast than segmentation. Second, most images suffer from unbalanced illumination make it harder recognize background. Third, symptom retinopathy unexpected shape, more difficult separate noises. Under such circumstance, research blood brought much attention been developed. this work, input is output will binary non-vessel pixels. Preprocessing with CLAHE enhancement, Vessel Extraction Otsu thresholding implemented along performance parameters Accuracy, Sensitivity Specificity. proposed work 20 used database called Digital Retinal Images Extraction. The Specificity, Sensitivity, Accuracy evaluated.